Review
-
DSV-Mem: Evaluating Multimodal Memory in Professional Workflows for MLLM Agents
2026-10-06 10:30:14Jike Zhong, Ritwick Chaudhry, Xuanbai Chen, Tianchen Zhao, Linghan Xu, Yifan Xing, Nishant SankaranAbstract
Conversational MLLM agents are increasingly expected to assist in professional workflows, from AI research and engineering design to product management and business operations. Yet this capability remains underexplored: existing benchmarks largely focus on informal, everyday interactions and personal-life scenarios featuring photographic natural images, isolated static artifacts, and recall-oriented questions. In contrast, professional scenarios often involve structured, information-heavy artifacts that undergo frequent revisions and authority updates, and compositional queries requiring reconciliation of many artifact versions while tracking state precisely. To address these challenges, we introduce DSV-Mem, a benchmark for evaluating Dense Stateful Visual Memory. DSV-Mem comprises expert-reviewed scenarios and 1,000 questions across five user-oriented categories (Current State, Past State, Derived State, Change History, and Conflict/Refusal). A Hartley-inspired criterion favors questions with broader visual-evidence inspection demands. We also introduce a generation harness that produces evaluation suites by decoupling state-transition synthesis from conversation filling. Evaluation over 27 configurations spanning frontier and open-weight models and memory management methods reveals that the strongest baseline scores below 45% on DSV-Mem. Analysis surfaces findings: 1) multimodality and information density both contribute to difficulty, but state evolution, particularly the number of governing updates, is the dominant tested factor. Raw conversation/haystack length, OCR, and arithmetic are not the primary bottlenecks; 2) models often fail to verify user premises against prior state updates before answering; 3) increased reasoning effort and memory management methods yield limited gains, whereas state-aware designs prove more effective. The benchmark and code will be publicly released.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08102
PDF
-
Leveraging a four-quadrant approach for evaluating Redpine Science
Abstract
Redpine Science gives models and agents a single access point to a wide range of peer-reviewed literature, queried directly through the Model Context Protocol (MCP) and an API. This report evaluates Redpine Science on two levels: the relevance of the retrieved chunks, and a model's answer when it has access to Redpine Science compared to web search. Both public and expert-validated benchmarks are used. Public benchmarks are a widely accepted way to test model development and are comparable across labs, but risk saturation and memorization. To address this, we complement them with an expert-validated question set. In total, this report presents four evaluations. On ScholarQABench SciFact, the public answer-quality benchmark reported here, an agent with Redpine Science answers 94.4% of claims correctly against 87.6% with no retrieval. On the expert-validated question set, an agent with Redpine Science states 80.1% of the required claims against 70.2% for an agent restricted to web search. On the 668 queries of a public retrieval benchmark whose gold paper Redpine holds, stripped of any model reasoning, Redpine Science places the correct source paper in its top ten results for 83.1% of queries (Recall@10), against 79.3% for the benchmark's creator. A blinded expert relevance panel places Redpine Science's Precision@5 at 75.2% against 39.8% for the PubMed search tool. We release the expert-validated question set and instructions to reproduce every headline result above, at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07937
PDF
-
SWE-Game: Can Coding Agents Build the Games We Want?
2026-10-06 07:03:14Xiaoyu Chen, Lai Wei, Jin Wang, Xiangyu Zou, Ruochen Fan, Enze Luo, Mingzhe Yao, Jiahui Zhu, Yuhua Wen, Linghe Kong, Weiran HuangAbstract
We introduce SWE-Game, a benchmark of 247 tasks grounded in 41 executable reference Godot games spanning 13 gameplay categories in 2D and 3D. Five task types cover development from a brief, implementation from a game design document, skeleton completion, repair of 83 injected-fault cases, and Godot-to-Unity porting. Reference materials specify the intended gameplay, while a shared instrumentation interface lets evaluator-owned drivers and probes execute actions and observe independently implemented games. Evaluation combines engine-state checks, certified reference-input replay, and agent-authored feature demonstrations to assess mechanic correctness, demonstrated playability, and behavioral restoration and preservation after repairs. Game-specific vision-language rubrics separately assess presentation. Across six models, Opus5 achieves the highest overall score in all five task types. Best overall scores remain below 60 out of 100 across the three construction tasks, with Brief-to-Game reaching 50.38. Analysis of reviewed submissions identifies requirement omissions and gameplay logic errors as predominant implementation problems. On human-labeled behaviors from 100 agent-built games, executable checks achieve 92.59% balanced accuracy, compared with 78.41% for a video-based VLM judge. Rubric-based visual scores reach a Spearman correlation of 0.829 with human ratings of 200 gameplay clips. Together, these results characterize current agent capabilities across game-development activities and support combining runtime evidence with visual assessment.
Abstract (translated)
URL
https://arxiv.org/abs/2609.33678
PDF
-
Contrastive Learning for Aspect Representation towards Explainable Recommendation
2026-10-06 04:55:55Emrul Hasan, Chen DingAbstract
In this work, we propose a novel recommendation model, CLARER (Contrastive Learning for Aspect Representation towards Explainable Recommendation) that integrates aspect features learned from textual reviews with rating information to improve the accuracy and explainability of recommendations. Our proposed framework learns user and item representations by combining rating-based features and aspect-based features from reviews. Specifically, rating-based features are learned through a multi-layer perceptron (MLP) model, while aspect-specific review representations are learned using a transformer encoder to capture the semantic information and contrastive learning to better distinguish user preferences. To provide explanations, we train a transformer decoder, using the final representations of users and items from both rating and aspect-based features as context. Experimental results in three benchmark data sets demonstrate that our model achieves superior performance compared to baseline methods in both recommendation (accuracy) and explanation generation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07761
PDF
-
A Survey on LLM-Integrated Hardware Design Verification
2026-10-06 03:20:59Hao Zheng, Jaime Rafael Imperial, Bardia Nadimi, Xiangfei KongAbstract
Large language models (LLMs) are increasingly being integrated into hardware verification to automate specification interpretation, verification-artifact generation, debugging, formal reasoning, and tool orchestration. This survey provides a systematic review of LLM-assisted hardware functional verification across SystemVerilog assertion generation, stimulus and testbench generation, bug localization and design repair, model checking and equivalence checking, SAT/SMT optimization, and emerging agentic verification workflows. We organize the literature by methodology, verification objective, tool interaction, benchmark, and evaluation criterion, and examine both inference-time techniques--including prompting, retrieval, structured reasoning, and agentic workflows--and training-time adaptation. Across these areas, a common pattern emerges: LLMs are most effective as semantic reasoning, search, and orchestration components embedded within verification-aware workflows, while simulators, formal engines, coverage tools, and solvers provide executable feedback and correctness evidence. However, tool acceptance alone does not establish verification correctness, since assertions, tests, repairs, or proofs may satisfy available checks without faithfully capturing the complete design intent. We therefore identify semantic alignment between specifications and verification evidence, scalable integration with deterministic tools, generalization to unseen designs, and rigorous evaluation of correctness, cost, robustness, and human effort as key challenges. Finally, we discuss emerging directions toward specification-centered, neuro-symbolic, and persistent agentic verification systems that combine LLM flexibility with independently checkable verification evidence.
Abstract (translated)
URL
https://arxiv.org/abs/2610.10580
PDF
-
Understanding Errors in LLM-Based Question Answering over Imperfect Tables
2026-10-06 03:12:30Baowen Zhang, Wei Fan, Ruman Wang, Hangting YeAbstract
Answering questions over imperfect tables requires handling errors that can affect the answer. We investigate two challenges for large language models (LLMs): whether error discovery depends on where errors appear in a table, and whether providing their locations is sufficient for accurate question answering (QA). Using human-reviewed instances from RADAR-T, we conduct controlled studies across three LLMs by varying row order and comparing original, error-marked, and repaired tables. First, reordering rows changes error discovery even when the table contents and gold answer remain unchanged. During direct inspection, LLMs are more likely to discover all rows containing relevant errors when these rows appear later in the table or are grouped more closely together. Second, providing verified error locations alone is insufficient for accurate QA: with code execution, accuracy on repaired tables exceeds that on error-marked tables by 39.0-59.1 percentage points across the three LLMs. As a practical application of these findings, we combine error discovery across shuffled table views with explicit guidance for verifying and handling the reported errors in a simple workflow, Geometry-Balanced Discovery and Intervention (GBDI). On RADAR-T, GBDI improves QA accuracy by 3.8-18.5 percentage points over a code-agent baseline across five LLMs (paired 95% confidence intervals exclude zero for four), at the cost of additional inference. These results highlight the importance of both reliable error discovery and effective error handling in QA over imperfect tables. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.04687
PDF
-
EIO-Agents: The Missing Semantic Layer for AI Agent Evaluation
Abstract
AI agents are entering production in increasingly consequential environments without a shared semantic standard for what their evaluations actually mean. Scores, traces, judge outputs, and multi juror findings are increasingly used to justify readiness and release decisions, yet they often do not specify what evidence supports a claim, what that evidence can establish, or how the claim leads to a decision. We introduce EIO-Agents, an open specification for interoperable AI agent evaluation built on two layers. The Evaluation Intelligence Ontology (EIO) provides the semantic layer through typed evidence, versioned behavioral predicates, evidence contracts, claims, witness rules, proof status, recurrence, and computable derivations for metrics, findings, controls, and PASS, REVIEW, or BLOCK decisions. The Portable Evaluation Record (PER) provides the system of record: a canonical, content addressed representation of one evaluation that preserves the evidence to decision chain and can be re derived, explained, and verified. Scores summarize, juries interpret, and traces record, but none of them define what the evidence means or what it can prove. EIO provides that missing semantic contract, while PER preserves the resulting evaluation as a portable and verifiable system of record. As AI agents assume greater operational responsibility, evaluation must become more than a collection of scores and verdicts; it must become an accountable artifact whose meaning, evidence, limitations, and decisions can be independently checked.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07675
PDF
-
Joint Workflow and Prompt Optimization for User Behavior Simulation
2026-10-06 02:59:54Nipun B Nair (Monash University), Tongtong Wu (Monash University), Hongzhi Yin (The University of Queensland), Hui Li (Xiamen University), Weiqing Wang (Monash University)Abstract
User behavior simulation is the computational modeling of user interactions within information systems through the use of simulated agents in place of live users. It supports system testing and evaluation, decision-making and forecasting, and user experience design. Existing simulators rely on hand-crafted rules or domain expertise that transfers poorly across tasks. SWORD (Simulation-driven Workflow and Prompt Optimization with Role-based Design) is introduced as a framework that jointly optimizes multi-agent workflow topology and natural-language prompts. It is guided solely by a scalar task metric, without domain initialization or task-specific engineering. The experimental results demonstrate that SWORD achieves statistically significant gains over prompt-only, workflow-only, and staged-optimization baselines under a controlled, identical-backbone comparison. Against the strongest published domain-specific baseline, SWORD further improves accuracy while using a smaller backbone model, substantially less training data, and a very reasonable API cost (\$4--\$6 for each dataset). Beyond predictive performance, SWORD autonomously discovers domain-relevant signals, review-sentiment mapping rules and epidemiological decay priors, purely from scalar error feedback, establishing textual gradients as a mechanism for unsupervised feature-importance discovery in user behavior modeling.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07663
PDF
-
Silicon Language: A Robot-Native Knowledge Exchange Framework for Heterogeneous Robots
2026-10-06 02:46:10Yi Liu (School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China, Yulin Saiyi Intelligent Technology Co., Ltd., Yulin, China), Xianglin Meng (Yulin Saiyi Intelligent Technology Co., Ltd., Yulin, China), Chang Chen (Yulin Intelligent Unmanned Equipment Innovation Center Co., Ltd., Yulin, China), Jingjing Fan (Yulin Intelligent Unmanned Equipment Innovation Center Co., Ltd., Yulin, China)Abstract
Reusing a capability across heterogeneous robots still requires substantial human adaptation and verification: transferring a skill often means re-engineering interfaces, retuning parameters, and re-validating safety. We introduce Silicon Language, a robot-native knowledge exchange framework that treats the robot as the active subject of its own capability evolution. In this framework, a robot that wants a capability encodes its own experience into knowledge packets, publishes them, retrieves peer packets, translates them for its own sensors and actuators, and reviews them through independent local trial. A receiver-side usability evaluation procedure lets each robot decide for itself whether an external packet is useful, and progressive blending with automatic rollback is designed to reduce the risk of negative transfer when adopting it. The system combines three infrastructure layers (edge agent, Silicon Transfer Protocol (STP), and knowledge hub) with a capability stack inspired by the human scholarly system. We report a 30-day proof-of-concept deployment at an above-ground simulated-mine laboratory in Yulin, with following trials on an outdoor sand road and an indoor factory floor. Two heterogeneous robots encoded and translated three capabilities across embodiments through operator-assisted file copies mediated by the Silicon Language translation layer; source-side trials of the dust-locked following behavior were recorded on Taurus. Project records indicate that per-capability adaptation time dropped from days to hours; we present these figures as descriptive deployment records rather than controlled measurements. The deployment provides initial evidence for cross-embodiment knowledge exchange; fleet-level autonomous evolution and controlled with/without-packet comparisons remain future work.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07650
PDF
-
LOGIC: An LLM Benchmark for Intent-Grounded Change Impact in Aerospace Electrical Systems
2026-10-06 01:14:09Muhammad Faraz Shoaib, Muhammad Qasim, Raisulhaq Mohammed Rizwan, Rahmatullah Safdar, Muzammil Adnan Shaik, Abdul Aleem MohammedAbstract
Aerospace electrical-design revisions can contain multiple genuine changes, although an engineering request may authorize only a subset. Propagating every detected difference can therefore produce overly broad impact reports. We present LOGIC, a controlled benchmark and evaluation framework in which locally deployable language models ground a request in a deterministic candidate-change inventory before selected changes are propagated through a typed electrical traceability graph. This separation permits candidate-selection errors to be distinguished from downstream propagation errors. LOGIC contains 168 scenarios, including 144 selection and 24 abstention cases. We evaluate three 7--8B models against intent-agnostic, lexical, and structured-evidence methods, with an oracle-root upper bound. On 96 explicitly anchored selection cases, gate-only structured evidence achieves candidate F1 of 1.0000, compared with 0.9677 for token-lexical matching. On 12 relational-paraphrase cases, token-lexical F1 is 0.1772 and gate-only F1 is 0.0000, compared with 0.5000--0.6400 for the large language models. Model grounding degrades as candidate inventories grow from 4 to 64 changes, while affected-element and typed-path accuracy remain comparatively stable when frozen selections are replayed over graphs of approximately 1K to 100K nodes. Strict evidence gating suppresses false positives but can remove correct semantic selections. An exploratory evidence-empty abstention policy raises strict abstention accuracy to 0.6667 for all three models and reduces unsafe-report rates to 0.1667, while decreasing answerable-case coverage by 16.0--27.1 percentage points. Four of six conflicting requests remain unsafe for each model. These findings support combining literal evidence and language-model reasoning with engineering review when intent cannot be established reliably.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07580
PDF
-
MRPilot: Supervising and Intervening LLM-Based Multi-Robot Teams through Mixed Reality
2026-10-05 22:40:55Xiaoran Yang, Xun Qian, Yang Zhan, Nathan Tran, Ziyi Liu, Qiao JinAbstract
Large language models (LLMs) let users direct heterogeneous multi-robot systems (MRS) through natural language, but make task interpretation, robot assignment, and coordination difficult to inspect and change. Based on a formative study with 12 non-expert users, we developed MRPilot, a mixed reality system organized around four stages of supervision and intervention. MRPilot represents robot-team plans and execution states as structured commitments shared across synchronized situated and overview views. Across four stages, it helps users resolve ambiguous references (Forming), review plans before execution (Reviewing), monitor distributed execution (Following), and make robot-level or team-level changes when problems arise (Repairing). In a within-subjects study with 20 participants in a virtual reality-simulated home, MRPilot reduced workload, increased situational awareness, transparency, trust, and perceived control compared with a conventional LLM-based conversational interface using the same LLM planner and robot capabilities. We provide design implications for multi-scale intervention, adaptive supervision, and calibrated reliance in LLM-based MRS.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07477
PDF
-
PsyCIDRA: A Dual-Agent Framework for Psychiatric Interviewing and Diagnostic Reasoning
2026-10-05 22:40:24Milad Mohammadi, Fatemeh Akrami Shamsabadi, Zahra Mohseni, Amirhossein Safdarian, Malekfarhad Malek, Hadi Moradi, Hesham FailiAbstract
Large language models show promise in clinical reasoning, but psychiatric interviewing requires guiding an evolving conversation. Their ability to carry out this interactive assessment remains less studied. We present PsyCIDRA, a dual-agent framework linking free-form psychiatric interviewing with diagnostic reasoning for expert review. Its interviewer agent uses tools to maintain working notes, load expert-written skills, and retrieve ICD-11 references to guide inquiry. Its diagnostic reasoning agent then receives the completed interview transcript and reports hypotheses alongside supporting, conflicting, and missing evidence, withholding a final hypothesis when none is sufficiently supported. Using patient profiles generated with PsyCPG, we first evaluate PsyCIDRA in simulation. Across four models on 53 evaluation cases, it achieves higher diagnostic agreement than direct prompting. On 81 held-out simulated cases, rank-1 accuracy is 60.5% versus 51.9%. In a blinded study of 101 human participants in separate arms, PsyCIDRA agrees with psychologists on whether to propose a diagnostic hypothesis in 79.6% of cases, compared with 65.4% for direct prompting. Together, these findings support the potential of LLM agents to assist psychiatric assessment through free-form dialogue. By examining diagnostic reasoning, interview quality, and safety together, this study contributes to understanding the capabilities and limitations of psychiatric interview agents.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07473
PDF
-
When Does AI Supervision Help? A Role-Aware Study of Network Fraud Decision Management with Blockchain Auditability
2026-10-05 21:40:07Saviz Changizi, Nasibeh Mohammadzadeh, Mohammad Shojafar, Rahim TafazolliAbstract
When does a second artificial intelligence (AI) component improve a primary network-fraud decision rather than add operational burden? We study this question through a role-aware Decider-Supervisor (DS) framework with blockchain auditability, evaluating four directional configurations that combine centralised machine learning, a Federated Averaging (FedAvg)-trained federated meta-model, and Base or Quantized Low-Rank Adaptation (QLoRA) large language model variants. The analysis compares primary-only and supervised decisions using non-hard fraud performance, intervention burden, conditional calibration, traffic-mix and Review-capacity sensitivity, dependability tests, and blockchain lifecycle controls. The deterministic hard gate resolves 89.994% of fraudulent requests, leaving the non-hard population as the main AI decision setting. Conditional validation calibration does not produce a consistently transferable supervisory advantage on deployment replay. DS-3 QLoRA is the least disruptive supervised configuration, but it still underperforms its primary FedAvg stage in F1 and total errors. Across 36 reweighted traffic mixtures, supervision reduces total errors only for DS-4 Base in two extreme high-fraud scenarios. Blockchain tests support digest verification, tamper detection, authorisation, single-use review resolution, and post-finalisation integrity, while exposing a pre-finalisation single-write limitation. The results show that the value of AI supervision depends on role assignment, calibration, escalation policy, traffic composition, and lifecycle controls rather than on the presence of a second model alone.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07434
PDF
-
Who Wrote It Is Not Enough: Detecting Who Contributed the Insight
2026-10-05 20:34:03Zhuoyang Zou, Abolfazl Ansari, Jiaxi Yang, Delvin Ce Zhang, Qian Chen, Dongwon Lee, Wenpeng YinAbstract
As LLMs increasingly assist scientific writing and peer review, detecting who wrote the text is no longer sufficient: we need to determine who contributed the underlying insight. We introduce Insight Provenance, the task of identifying whether a review insight originates from a human, an LLM, or their hybrid contribution. We construct InsightProv-v0 from 4,057 scientific papers and 12,660 human reviews, simulating different levels of LLM involvement with GPT-4o, Gemini, and DeepSeek and annotating provenance at the sentence level. We show that strong performance on raw data can be misleading, as models exploit linguistic and textual-authorship shortcuts that degrade substantially under progressively debiased evaluation. We therefore propose a two-stage adversarial framework that suppresses shortcut signals while preserving provenance-relevant information. Beyond detection, extensive analyses reveal what makes intellectual authorship identifiable: paper grounding and neighboring review context provide complementary provenance signals, while human, hybrid, and AI insights systematically differ in their information sources and failure modes. Most strikingly, AI insights predominantly remain close to generic or paper-provided information, whereas human insights more often introduce external knowledge and independent judgment. These findings suggest that while wording can be rewritten by an LLM, the provenance of an idea leaves a deeper and more persistent signal.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07365
PDF
-
Evaluate the Stack, Not the Layer: Do Deterministic and LLM Gates for Agent Actions Fail Independently?
Abstract
Runtime gates for agent tool calls are stacked on the assumption that their errors multiply. We test it on 1,119 labelled agent actions from three corpora, without an adaptive adversary. The stack has one deterministic rule layer and four LLM judges, three of them re-collected with the served model recorded on every call. We read each stack as a number of multiplication-equivalent layers, n_mult, with its floor under perfect coupling. Under the STRICT miss definition (escalation to a human scored as not stopped), any two judges compose to about 1.2 to 1.4 layers ({\phi} median +0.430, 6 of 6 pairs significant, floors 1.02 to 1.17). The rule layer plus one judge composes to 1.86 to 2.09 layers ({\phi} median +0.014, 0 of 4 significant, floors 1.01 to 1.09). Under PRIMARY (escalation scored as caught) the bands are 1.21 to 1.57 and 1.80 to 2.13. Intervals separate on the pooled data, point estimates split on each corpus, and a third-vendor judge lands in the judge band. Solo accuracy does not predict what a layer adds: a cloud rule pack lowers the rule layer's solo miss rate by 20% and adds no new joint coverage. The difficulty share of judge coupling is not identifiable: 31.8% to 61.8% depending on the probe and the miss definition. One judge tier was served by an unrequested model version in 50 of 112 batches, concentrated on the external corpus. That event overturned a pre-declared analysis rule, and the scoring of review verdicts reversed five conclusions. We report both.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07359
PDF
-
From Sandbox to Enforcement: Confidence-Qualified Threat Intelligence for Critical Infrastructure
2026-10-05 19:47:45Nikolaos Kekatos, Mihaela Curc\u{a}, Georgios Koutidis, Mihai Nena, Tom Nianios, Robert-\c{S}tefan \c{S}andru, Michael Ioannou, Charalambos BratsasAbstract
Security operations centres and national incident-response teams defending critical infrastructure collect abundant threat data yet struggle to turn it into actionable intelligence. A malware sandbox produces detailed behavioural evidence, but as a large, unranked report whose confidence is unstated. We present CG-CTI, an operational pipeline that converts live sandbox output (CAPEv2) into STIX 2.1, correlates it in a knowledge graph with other critical-infrastructure sensors, and attaches to every intelligence object an explicit confidence status derived from provenance, cross-source corroboration, and observation durability. This status gates automated action: only corroborated intelligence is eligible for automated enforcement, while lower-confidence objects are routed to analyst review or kept as context. A grounded language-model stage then narrates the confidence-qualified evidence, where each statement either cites a supporting object or is marked unsupported, so fabricated references are removed before analyst review. We implement CG-CTI within the CYBERGUARD project, whose consortium includes Romania's national cyber-security directorate, and evaluate it against the live sandbox on a labelled malware corpus, measuring conversion validity, indicator yield, technique coverage, corroboration, enforcement eligibility, latency, and summary grounding. CG-CTI turns fragmented sandbox output into corroborated, confidence-ranked, and auditable intelligence for critical-infrastructure defence.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07310
PDF
-
Catching Developers in the Flow: Low-Latency Agentic Program Repair at Google Scale
2026-10-05 19:23:06Celal Ziftci, Spencer Greene, Ray Liu, Livio Dalloro, Lorenzo DiniAbstract
Manual repair of program failures is time-consuming and disruptive for software developers, particularly during the pre-submit phase where test failures occur within continuous integration systems. While Automated Program Repair has seen significant advancement through Large Language Models, existing state-of-the-art techniques primarily focus on post-submit workflows, operating offline without the low-latency requirements necessary to assist developers in real-time within their flow before they switch context. In this paper, we introduce FlowAgent, an AI agent deployed at Google to automatically repair test failures in the pre-submit outer-loop workflow inside continuous integration systems. Integrated into Google's internal developer tools, Critique and Cider,FlowAgent utilizes a ReAct-style generate-and-validate loop, as well as rigorous pre-execution and post-execution abstention filters to ensure high-quality suggestions under strict latency constraints. Based on our case studies, FlowAgent is highly effective. First, a manual evaluation conducted on 195 real-world test failures demonstrated 67.18% accuracy in suggesting correct fixes. Following its Google-wide deployment, FlowAgent suggested fixes on 295,508changes, of which developers previewed 65,069 and applied 28,554. Developer feedback from interviews indicate that the agent is useful in suggesting correct fixes, integration of autonomous repair agents into industrial software engineering workflows is received well, while interesting challenges and opportunities still remain.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07289
PDF
-
Can Semantic Geometry Teach an AI Judgement?
2026-10-05 18:49:55Thomson D. Nguy (Radiant Institute for Manifold Studies)Abstract
How can an AI agent determine what rules to follow? One rule permits an action. Another imposes a condition, exception, or conflicting obligation. Deterministic systems can resolve those relationships when they have been specified. When they remain implicit in language, an agent can follow one rule while missing another that should stop it. Refusing every unresolved action avoids that risk, but also blocks permissible actions. We wanted the agent to make the distinction and still act. Our initial hypothesis was that geometric measurements could supply a basis for judgment. We represented actions and policies as vectors, then tested whether their geometry could identify governing policies and interpret the action's relation to them. Across four studies, the tested approaches did not establish reliable pre-action judgment. In the final synthetic study, a lexical router recovered every governing and blocking policy while reducing median policy checks by 97.7%. The composed pipeline nevertheless escalated all 2,304 test actions, including those it should have allowed. Supplying every policy to the same downstream mechanism changed no decision. Finding the policies had not solved the problem of interpreting them. This result led us to revise our hypothesis: judgment in AI agents requires developing a consequence graph. Such a graph would connect the actor and authority to policy conditions, exceptions, and the changes an action would produce. Follow-on studies will ask whether making those relationships explicit helps the agent distinguish when to act, stop, or seek review.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07249
PDF
-
Forecasting the Growth of Social Media Information Cascades: Towards Human-in-the-Loop Misinformation Triage
2026-10-05 18:24:18Ansh Gupta, Abhiram Gorle, Aayush Rajesh, Tsachy WeissmanAbstract
Limited review teams must identify which emerging claims are likely to keep growing before their eventual reach is known. We center early misinformation triage on this continuation-forecasting problem: predicting subsequent recorded propagation-tree growth from the first 30 minutes of activity. On FibVID, we compare early node count with structural depth entropy, temporal arrival entropy, and their pair while keeping all propagation trees from each original claim in one partition. Across 352 test trees from 59 claim groups separate from training, the combined model raises $R^2$ for log-transformed future growth from 0.307 to 0.323 and reduces log-MAE by 2.4% (95% claim-bootstrap CI, -0.4% to 5.2%). The gain is especially pronounced among 97 high-activity trees: $R^2$ rises from 0.248 to 0.395, Spearman's $\rho$ from 0.394 to 0.529, and log-MAE falls by 11.7% (95% CI, -1.9% to 23.9%). Complementing the 30-minute growth forecast, we analyze the first 15 replies in 563 PHEME threads. In this cohort, the 15th reply arrives after a median of 28.8 minutes; 52.0% reach the fixed reply prefix within 30 minutes and 71.6% within one hour. Even without the LLM-generated factual-accuracy dimension, the remaining stance, communicative, and affective state composition retains cross-event ranking signal (ROC-AUC 0.538); including that dimension increases ROC-AUC to 0.562. In a separate Check-COVID evaluation of 229 claims, reciprocal-rank fusion retrieves a gold evidence document within the top five for 74.2% of claims and within the top 20 for 94.3%; sentence reranking reaches Recall@20 of 58.1%. We propose an integrated human-review system that brings these early forecasts, response patterns, and retrieved evidence together for misinformation triage relying on the potential virality of claims.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07209
PDF
-
A Data-Centric Review of Plant Disease Datasets: Taxonomy, Critical Analysis, Environmental Variability, and Implications for Precision Agriculture
2026-10-05 12:34:24Aamir Hilal, Shabir Ahmad Sofi, Neeraj GoelAbstract
Despite rapid advances in artificial intelligence, reliable real-world plant disease detection remains a persistent challenge. Visual and deep learning approaches have shown promising results, but their deployment under field conditions remains limited. A key bottleneck is the reliance on laboratory-generated datasets that lack environmental diversity, realistic backgrounds, and balanced class distributions, resulting in poor generalization. In contrast, datasets collected directly from agricultural environments capture natural variability and better reflect challenges faced by farmers across regions. This review presents a critical analysis of visual and deep learning approaches for plant disease detection, with emphasis on plant disease datasets. It establishes a taxonomy based on acquisition setting, accessibility, plant diversity, disease composition, class structure, and imbalance severity, and examines their implications for model generalization and real-world deployment. A comparative analysis of laboratory and real-field datasets identifies critical gaps that hinder disease detection. The review further analyzes how multi-level dataset imbalance, including intra-class, inter-crop, and cross-dataset imbalance, and limited environmental variability affect model performance and robustness, an area insufficiently examined in existing surveys. Beyond image-based approaches, it highlights the importance of integrating environmental parameters such as temperature, humidity, and leaf wetness with image data to improve prediction under dynamic field conditions. Finally, the review identifies key challenges, research gaps, and future directions concerning dataset construction, environmental variability, structural imbalance, standardization, and multimodal disease monitoring. It provides a foundation for developing next-generation multimodal frameworks for precision agriculture.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07087
PDF
